Room 203, 2/F, Cheng Yu Tung Building (CYT) The Chinese University of Hong Kong November 3rd, 2025

Abstract: Edge computing provides a new way to implement services with many unique advantages. While many edge computing solutions have been implemented within different network infrastructures, in this talk, we will explore ways to design a lightweight edge computing platform which is robust and portable, leading to interesting applications and services in sustainability, public safety, and many more application domains.

Biography: Suman Banerjee is the David J. DeWitt Professor in Computer Sciences and Electrical and Computer Engineering at the University of Wisconsin-Madison, where he is the founding director of the WiNGS laboratory. Along with students, he has published more than 100 papers in the top conferences and journals in his field. He has received multiple awards for papers published, including at venues such as ACM MobiCom, ACM CoNEXT, IEEE Dyspan, and ACM Mobigames. He is a recipient of the US National Science Foundation CAREER award, and ACM SIGMOBILE’s inaugural Rockstar Award (for early career achievements in the field). He has served as the Editor-in-Chief of Mobile Computing and Communications Review, as a Technical Program Chair of ACM MobiCom. He served as the chair of the steering committee of the ACM/EEE Transactions on Networking and serves as a member of the ACM MobiCom steering committee. He was the Chair of ACM SIGMOBILE from 2013 to 2017. He is a fellow of the ACM and of the IEEE.

Abstract: In a world where machines can see and speak, the next frontier is helping them truly listen. This talk explores superhuman and proactive acoustic AI systems that don’t just hear sounds, but understand human intent and act intelligently in real time. We’ll dive into two core innovations: superhuman hearing, which enables AI to separate and interpret sounds and conversations even in crowded, noisy environments and proactive assistance, where the system anticipates human needs and offers timely help without being prompted.

Biography: Shyam Gollakota is a Washington Research Foundation endowed Professor at the Paul G. Allen School of Computer Science & Engineering in the University of Washington. His work has been licensed by ResMed Inc, our startup Sound Life Sciences acquired by Google, and is in use by millions of users. He was also CEO of a startup where we obtained FDA 510(k) clearance for the technology developed in my lab. His lab also worked closely with the Washington Department of Agriculture to wirelessly track invasive "murder" hornets, which resulted in the destruction of the first nest in the United States. He is the recipient of the ACM Grace Murray Hopper Award in 2020, a Moore Inventor Fellow in 2021 and more recently the InfoSys prize in 2024. He was also named in MIT Technology Review's 35 Innovators Under 35, Popular Science 'brilliant 10' and twice to the Forbes' 30 Under 30 list. His group's research has earned Best Paper awards at MOBICOM, SIGCOMM, UbiComp, SenSys, NSDI and CHI, appeared in interdisciplinary journals like Nature, Nature Communications, Nature Biomedical Engineering, Science Translational Medicine and Science Robotics as well as named as a MIT Technology Review Breakthrough technology of 2016 as well as Popular Science top innovations in 2015. He is an alumni of MIT (Ph.D., 2013, winner of ACM doctoral dissertation award) and IIT Madras.

Abstract: Wireless is a pivotal aspect of the AIoT -- with its traditional role being to network distributed devices in order to create distributed intelligence. In this talk, I will touch upon two other important roles of wireless that offer substantial value to AIoT, but are traditionally under-explored. First, advances in wireless sensing, which historically have been employed in large radar platforms, are now available in chip-sized platforms that readily integrate into AIoT devices. I'll speak about my own research group's efforts in exploring how these platforms open up entirely new AI-driven applications in domains ranging from autonomous vehicles, and augmented reality to digital health. Next, an oft-ignored aspect of wireless is that at a fundamental level, it is simply a source of energy. Indeed, we experience this aspect of wireless in our own kitchens in the form of a microwave oven. I'll describe our group's efforts in rediscovering how microwave heating can benefit from advances in wireless communication and sensing, benefiting not only cooking but new domains ranging from robotics to healthcare.

Biography: Swarun Kumar is the Sathaye Family Foundation Professor at Carnegie Mellon University's ECE department, with an affiliate appointment in the CS department, the HCI Institute and the Cylab Security and Privacy Institute. Swarun heads the laboratory for emerging wireless technologies (WiTech lab). He designs and builds novel systems to enable faster wireless networks and new services. His research has impacted a wide-range of domains ranging from low-power wide-area networking, wireless localization, RFID systems, mmWave sensing and satellite networking. Swarun is a recipient of the 2024 ACM SIGMOBILE Rockstar award, the 2021 ACM SIGBED Early Career Researcher Award, the NSF CAREER award and the Google Faculty Research Award.

Abstract: While keyboard typing has been the most common way of inputting texts, handwriting still plays an important role in generating, inputting, or recording information like filling out essential/private forms. Considerable research has been done to identify and demonstrate the risk of keystroke-inference attacks. However, little has been done on handwriting inference despite its high risk of leaking sensitive information. To assess this under-explored risk of information leakage, we present a novel handwriting-inference attack, called HW-Spy, by tracing the victim’s pen-tail movements when both the pen tip and the writing surface are outside the view of the attacker’s camera, which usually happens when the victim is multitasking during an online meeting, when the victim’s writing scene (in a public space) is recorded by a remote camera, or when the victim’s writing behaviors are captured by the surveillance camera in a bank/dealership/realty office. In particular, we apply image segmentation to the recorded video frames of the victim’s writing activities and extract the victim’s pentail movements as a 2D coordinate sequence. We then identify the stroke-associated movements from the recorded pen’s in-air video frames using a 1D U-Net model trained for stroke mask prediction and segment the characters based on the thus-derived motion features. The pen-tail’s coordinate segments are then fed into a Long Short-Term Memory (LSTM) network to reconstruct the actual handwriting, which is processed further by a transformer-based model to infer the hand-written content. Our extensive experimentation shows HW-Spy to achieve an accuracy, up to 84.2%, of personalized handwriting inference and a comparable accuracy, up to 79.5%, of non-personalized handwriting inference. This is joint work with Long Huang, a PhD student of mine and will be presented at the 2025 ACM CCS.

Biography: Kang G. Shin is the Kevin & Nancy O'Connor Professor of Computer Science at the University of Michigan, Ann Arbor. His research focuses on QoS-sensitive computing, networking, and embedded real-time cyber-physical systems including autonomous vehicles. He has supervised 93 PhD completions and authored/coauthored nearly 1,000 technical articles, a textbook, and about 60 patents. His notable awards include the 2023 IEEE TCCPS Technical Achievement Award, 2023 SIGMOBILE Test-of-Time Award, 2019 Caspar Bowden Award, and Best Paper Awards from multiple prestigious conferences including MobiCom'11 and USENIX. He received the 2006 Ho-Am Prize in Engineering (highest honor for Korean-origin engineers) and several University of Michigan institutional awards including the Stephen Attwood Award in 2004. He has chaired major conferences including 2009 ACM MobiCom and 2005 ACM/USENIX MobiSys, and is a fellow of both IEEE and ACM. He has served on government committees including the US NSF Cyber-Physical Systems Executive Committee and has helped found several startups.

Abstract: Autonomous driving perception operates based on constrained resources and in the environment that contains benign and adversarial disturbances. This talk first considers the adversarial scenario where there might exist physically deployable adversarial example attacks in the road environment. I will present our recent studies on both attacks and defenses. Then, I will present our new advances on the resilience of autonomous driving perception against system variations including vehicle speech changes and edge-cloud link quality changes for cloud-assisted vehicles.

Biography: Rui Tan is a Professor at the College of Computing and Data Science, Nanyang Technological University (NTU), Singapore. Prior to his employment by NTU, he was a Research Scientist (2012-2015) and a Senior Research Scientist (2015) at Advanced Digital Sciences Center (ADSC) of the University of Illinois at Urbana-Champaign, and a postdoctoral Research Associate (2010-2012) at Michigan State University. He received the Ph.D. (2010) degree in computer science from City University of Hong Kong, the B.S. (2004) and M.S. (2007) degrees from Shanghai Jiao Tong University. His research interests include cyber-physical systems and the Internet of Things, and in particular, the non-functional aspects of these systems, including security, safety, and resilience. He is the recipient of the Best Paper Award, Best Paper Award Runner-Up/Finalist from ICCPS 2022 and 2023, SenSys 2021 and 2022, IPSN 2014 and 2017, and PerCom 2013. He serves as Associate Editor for IEEE Transactions on Mobile Computing and ACM Transactions on Sensor Networks, TPC Co-Chair of e-Energy’23, EWSN’24, SenSys’24, and General Co-Chair of e-Energy’24 and RTCSA'25.

Abstract: Millimeter-wave (mmWave) radar offers compelling advantages over other sensing modalities, including all-weather/all-day operation, direct velocity measurement, strong penetration capability, and inherent privacy preservation. Leveraging these benefits, our research explores various perception tasks implemented across different data representations, such as raw signals, heatmaps, and point clouds. This presentation will detail our recent advancements in mmWave radar sensing tailored for autonomous driving and smart home applications, covering topics from robust on-vehicle and roadside sensing to fine-grained human-centric perception.

Biography: Yanyong obtained her B.S. from USTC in 1997, and her Ph.D. from Penn State in 2002, both in Computer Science. In July 2002, she joined the Electrical and Computer Engineering Department and Winlab at Rutgers University as an Assistant Professor. She was promoted to an Associate Professor with tensure in 2008, and a Professor in 2015. In July 2018, she moved back to her alma mater -- School of Computer Science at USTC. She has served on many organization committees sand TPC committees for international conferences. In the year of 2022, she serves as the TPC co-chair for ACM/IEEE IPSN. She has served as the Associate Editor for the following journals: IEEE TCC (cloud computing), IEEE TDSC, IEEE/ACM ToN, IEEE TMC, IEEE TSC, and Elsevier Smart Health. She is the winner of ACM Mobicom 2021 Best Paper Runner-Up Award.

Abstract: Commodity devices, such as smartphones and wearables can harvest rich but noisy physical signals. When properly modeled, these signals reveal fine-grained physical phenomena and transform these everyday devices into dependable tools for measurement and verification. In this talk, I will present our work on how we have fused physical signal models with lightweight learning to interpret complex phenomena from commodity sensors—acoustic, optical, inertial—to detect counterfeit liquid product, test mask filtration efficiency, combat digital image theft, and build virtual keyboard. Together, they demonstrate that embedding physical insight within inexpensive, everyday platforms can enable reliable sensing applications without reliance on specialized or costly instrumentation.

Biography: Mun Choon CHAN graduated with a BS in Computer and Electrical Engineering from Purdue University and Ph.D. from Columbia University. He was a Member of Technical Staff in the Networking Research Laboratory, Bell Labs, Lucent Technologies before joining the National University of Singapore (NUS) in 2004. He is currently a Professor and Vice Dean of Graduate Studies of the School of Computing (SoC), as well as the Lab Director of the NUS-NCS Joint Laboratory. He has published more than 140 conference/journal papers and has been awarded 7 US patents. He has won three best paper awards (ICNP 2019, SOSR 2019, ICDCN 2016) and was awarded the Facebook Networking Systems Research Award in 2019. His current research includes mobile sensing, programmable networks and 5G networks.

Panelist 1: Chenren Xu

Biography: Chenren Xu is a Boya Young Fellow Associate Professor, Deputy Director of Institute of Networking and Energy-efficient Computing and Assistant Dean of School of Computer Science at Peking University. His recent research interests focus on embodied AIoT and wireless AI for science. He earned his Ph.D. from WINLAB, Rutgers University, and worked as postdoctoral fellow of Carnegie Mellon University, guest professor of Keio University and visiting scholars in AT&T Shannon Labs and Microsoft Research. He serves as an Editor of ACM IMWUT, Associate Editor of Nature npj Artificial Intelligence, General Chair of UbiComp’26 and MobiSys’25, TPC Chair of UbiComp’25 and HotMobile’24, and General Secretary of ACM SIGBED China. He is a recipient of MobiSys’25 Best Paper Award, CCF Technological Invention Award, Okawa Foundation Grant, ACM SIGCOMM China Rising Star and Alibaba DAMO Academy Young Fellow. His work has been featured in MIT Technology Review.

Panelist 2: Dongyao Chen

Biography: Dongyao Chen is an Assistant Professor of Computer Science at Shanghai Jiao Tong University (SJTU). He received his Ph.D. in Computer Science and Engineering from the University of Michigan - Ann Arbor in 2020, advised by Prof. Kang G. Shin. His research interests lie in mobile sensing, wearable systems, and security/privacy issues of emerging sensing technologies. His research has been published in conferences such as MobiCom, MobiSys, UbiComp, SenSys, NDSS, and CCS. His work received the Distinguished Paper Award at UbiComp 2025 and the Best Paper Award at VehicleSec 2023.

Panelist 3: Stephen Xia

Biography: Stephen Xia is an assistant professor in the Department of Electrical and Computer Engineering at Northwestern University. His research lies at the intersection between systems, embedded machine learning, and signal processing, spanning areas in mobile and embedded computing, Internet-of-Things, cyber-physical systems, artificial intelligence, and smart health. His work focuses on realizing truly intelligent and autonomous environments by embedding and utilizing compute, perception, actuation, storage, and networking resources commonly found all around us. Stephen’s research has been highlighted by many popular media outlets, including Mashable, Fast Company, and Gizmodo, and has received various distinctions including multiple Best Demo Awards, Best Presentation Awards, and Best Paper Awards. Prior to Northwestern, Stephen was a postdoctoral scholar at UC Berkeley, received his Ph.D. from Columbia University, and received his B.S. from Rice University, all in Electrical Engineering.

Panelist 4: Binbin Xie

Biography: Binbin Xie is a tenure-track assistant professor in the Department of Computer Science and Engineering at The University of Texas at Arlington. She earned her Ph.D. from the Manning College of Information and Computer Sciences at the University of Massachusetts Amherst, under the supervision of Prof. Jie Xiong and in close collaboration with Prof. Deepak Ganesan. Her research focuses on wireless sensing, mobile health, cyber-physical systems, smart IoT, and wireless networking. Her work has been published in top-tier conferences such as MobiCom, MobiSys, SenSys, UbiComp and MobiHoc. Her research is supported by Risng STARs Award, UT System. She was a recipient of the Google Ph.D. Fellowship in mobile computing, was featured as an Emerging Rockstar by IEEE Pervasive Computing magazine, and received the MobiCom 2022 Best Community Paper Award Runner-up.